© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1646
    Prev
    Next
    INDEX
    Explanations

    references to negative aspects or critiques related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dime
    -0.76
     slices
    -0.73
     pages
    -0.72
     flakes
    -0.69
     Dome
    -0.69
     quotations
    -0.67
     SHARES
    -0.67
     sections
    -0.65
     loopholes
    -0.64
     helmets
    -0.64
    POSITIVE LOGITS
    uber
    0.97
    imental
    0.92
    artisan
    0.90
    igious
    0.86
    otic
    0.85
    raft
    0.84
    igor
    0.84
    lus
    0.84
    llah
    0.83
    wer
    0.82
    Activations Density 0.048%

    No Known Activations